SOURCE-LINKED INTELLIGENCE

ReFigBench: Benchmarking Scientific Figure Reconstruction as Editable PowerPoint Artifacts

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Multimodal coding agents are expected to turn visual inputs into usable artifacts, and they act through a harness, the layer of tools, context management, and execution environment around the model. Existing evaluations often isolate short tool calls, API traces, or screenshot resemblance, and a low score under these proxies cannot say whether the model saw poorly, planned poorly, or was failed by its harness. We study scientific overview figure reconstruction, an agent task in which a source image must become an editable PowerPoint slide that preserves text, topology, layout, and native docum

Read original source ↗ Open in workspace

recordType

paper

region

Global